Can the Tesla V100 run Qwen3 32B?
Yes, with 32 GB or more. Qwen3 32B needs about 22 GB and the Tesla V100 has 32 GB of VRAM. Expect about 25 tok/s, about reading speed. The 16 GB version doesn't have room.
ollama run qwen3:32bFirst time? Install Ollama, then paste that into a terminal.
Qwen3 32B needsAbout 22 GB
Tesla V100 has16 or 32 GB VRAM
Bandwidth900 GB/s
Estimated speed~25 tok/s
By memory size
Each Tesla V100 version
- 16 GBToo big
- 32 GBUsable ~25 tok/s
Want it faster?
Speed comes from memory bandwidth: the card reads all 20 GB of active weights for every token. On the Tesla V100, Qwen3 30B-A3B runs at about 160 tok/s if you can trade some quality for speed. Cards that run Qwen3 32B faster:
How we estimate
Speed is roughly memory bandwidth divided by the weights read per token, calibrated on our own rack. Sizes are Ollama's default 4-bit downloads plus about 1.2 GB for context. Real results are usually within about a third. Measured it yourself? Send us the number.
Keep going